Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to measurements or dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    et
    -0.16
    elman
    -0.15
    uce
    -0.15
    аÑĢаÑĤ
    -0.15
    rex
    -0.15
    ÙĨÚ¯ÛĮ
    -0.15
    224
    -0.14
    cloth
    -0.14
     Redemption
    -0.14
    uka
    -0.14
    POSITIVE LOGITS
    ilded
    0.20
    apers
    0.19
    ues
    0.17
    rove
    0.17
    he
    0.17
    hey
    0.17
    ateway
    0.16
    amage
    0.16
    isser
    0.16
    lish
    0.15
    Act Density 0.042%

    No Known Activations